[R] Uncorrelated random vectors

Greg Snow Greg.Snow at imail.org
Wed Jul 8 18:09:08 CEST 2009


The mvrnorm function in the MASS package has an argument to force the generated data to have the exact mean/variance structure as specified which when used with a diagonal variance matrix will generate data that has a 0 (within round off error) correlation in the data.  No post processing by Gramm-Schmidt or other methods needed.  The author(s) of the function cleverly hid this feature by placing the information on the help page for the function.

-- 
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at imail.org
801.408.8111

> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Moshe Olshansky
> Sent: Tuesday, July 07, 2009 9:10 PM
> To: r-help at r-project.org; Luba (AIM SE)Stein
> Subject: Re: [R] Uncorrelated random vectors
> 
> 
> As mentioned by somebody before, there is no problem for the normal
> case - use mvrnorm function from MASS package with any mu and make
> Sigma be any diagonal matrix (with strictly positive diagonal). Note
> that even though all the correlations are 0, the SAMPLE correlations
> won't be 0. If you want to create a set of vectors whose SAMPLE
> correlations are 0 you will have to use a variant of Gramm-Schmidt.
> I do not know whether a variant of mvrnorm exists for logistic
> distribution (my guess is that it does not).
> 
> --- On Tue, 7/7/09, Stein, Luba (AIM SE) <LUBA.STEIN at allianz.com>
> wrote:
> 
> > From: Stein, Luba (AIM SE) <LUBA.STEIN at allianz.com>
> > Subject: [R] Uncorrelated random vectors
> > To: "r-help at r-project.org" <r-help at r-project.org>
> > Received: Tuesday, 7 July, 2009, 11:45 PM
> > Hello,
> >
> > is it possible to create two uncorrelated random vectors
> > for a given distribution.
> >
> > In fact, I would like to have something like the function
> > "rnorm" or "rlogis" with the extra property that they are
> > uncorrelated.
> >
> > Thanks for your help,
> > Luba
> >
> >
> >
> >
> >     [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help at r-project.org
> > mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> > and provide commented, minimal, self-contained,
> > reproducible code.
> >
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.




More information about the R-help mailing list